Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.6075. Min Act: -0.1700
Data Index: 2306982 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.2950. Min Act: -0.1700
Data Index: 7042364 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.1700. Min Act: -0.1700
Data Index: 8499286 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.2325. Min Act: -0.1700
Data Index: 8328693 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.1388. Min Act: -0.1700
Data Index: 8037921 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.1075. Min Act: -0.1700
Data Index: 1706991 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.1075. Min Act: -0.1700
Data Index: 995319 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.1075. Min Act: -0.1700
Data Index: 271733 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.0763. Min Act: -0.1700
Data Index: 5553415 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2397691 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.0450. Min Act: -0.1700
Data Index: 7007900 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.0138. Min Act: -0.1700
Data Index: 304565 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.0138. Min Act: -0.1700
Data Index: 4865861 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6075. Min Range: -5.6075
Max Act: 5.0138. Min Act: -0.1700
Data Index: 86925 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6075. Min Range: -5.6075
Max Act: 4.9825. Min Act: -0.1700
Data Index: 967138 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6075. Min Range: -5.6075
Max Act: 4.9825. Min Act: -0.1700
Data Index: 5120528 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6075. Min Range: -5.6075
Max Act: 4.9200. Min Act: -0.1700
Data Index: 553347 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6075. Min Range: -5.6075
Max Act: 4.9513. Min Act: -0.1700
Data Index: 8078405 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6075. Min Range: -5.6075
Max Act: 4.9513. Min Act: -0.1700
Data Index: 1957916 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6075. Min Range: -5.6075
Max Act: 4.9200. Min Act: -0.1700
Data Index: 1026980 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19